INDEX

Explanations

phrases indicating responsibility or attribution

oai_token-act-pair · gpt-3.5-turbo

phrases indicating actions or states of being related to responsibility or culpability

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 scares

-0.65

Dur

-0.61

 extracts

-0.60

 masks

-0.60

 pops

-0.59

 edits

-0.59

 nets

-0.59

 hides

-0.59

 didnt

-0.58

 deficits

-0.58

POSITIVE LOGITS

asted

1.29

asting

1.23

asters

1.11

asty

1.06

pless

1.06

wered

1.05

lled

1.03

ying

1.01

ARC

0.98

othy

0.98

Activations Density 0.173%

phrases indicating responsibility or attribution

phrases indicating actions or states of being related to responsibility or culpability

No Comments

No Known Activations